def nonthreaded_get_filings(): # create object print 'getting filings using a single lonely execution thread :(' seccrawler = SecCrawler() date = '20170313' # date from which filings should be downloaded # date = '20160922' count = '100' # no of filings # sp_500 = open('missed_companies2.txt') sp_500 = open('sp_500.txt') lines = sp_500.readlines() sp_500.close() companies = [line.split('\t')[1:3] for line in lines[100:]] # OVERRIDES FOR TESTING # companies = [line.split('\t')[1:3] for line in lines[2:4]] # companies = [['AMZN', 'AMZN']] start = time.time() for companyCode, cik in companies: t1 = time.time() seccrawler.getFiling(str(companyCode), str(date), str(count), "10-K") # seccrawler.getFiling(str(companyCode), str(cik), str(date), str(count), "10-Q") # seccrawler.getFiling(str(companyCode), str(cik), str(date), str(count), "8-K") t2 = time.time() print "Total Time taken for ", companyCode, ": ", str(t2 - t1) end = time.time() print '\n\n\n FINAL TIME:' print end - start
def getSingleCompanyFiling(companyCode, logPath='downloaded_companies.txt'): date = '20170315' # date from which filings should be downloaded count = '100' # no of filings seccrawler = SecCrawler() t1 = time.time() try: seccrawler.getFiling(str(companyCode), str(date), str(count), "10-K") except: raise Exception("".join(traceback.format_exception(*sys.exc_info()))) # seccrawler.getFiling(str(companyCode), str(cik), str(date), str(count), "10-Q") # seccrawler.getFiling(str(companyCode), str(cik), str(date), str(count), "8-K") t2 = time.time() logString = "Total Time taken for " + companyCode + ": " + str(t2 - t1) f = open(logPath, 'a+') f.write(companyCode + '\n') f.close() return logString